© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21253
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.05
    3:0.03
    4:0.06
    5:0.53
    6:0.02
    7:0.04
    8:0.02
    9:0.11
    10:0.02
    11:0.03
    Negative Logits
    rouse
    -2.69
    RFC
    -2.58
    yip
    -2.57
     glim
    -2.51
    venge
    -2.46
    iage
    -2.41
    bilt
    -2.36
    assi
    -2.36
     culminated
    -2.33
    ynasty
    -2.24
    POSITIVE LOGITS
     weren
    5.21
     didn
    5.13
     neither
    5.07
     nowhere
    5.00
     doesn
    4.96
     never
    4.95
     Nope
    4.92
     wouldn
    4.88
     none
    4.87
     not
    4.79
    Activations Density 1.735%

    No Known Activations